INDEX

Explanations

references to organized crime groups or individuals involved in criminal activities

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ANCE

-0.86

éĸ

-0.82

ational

-0.73

OPLE

-0.69

++++++++++++++++

-0.69

 Tire

-0.66

______

-0.63

neath

-0.62

 Wonderland

-0.61

ACTED

-0.60

POSITIVE LOGITS

sters

1.12

iles

1.05

ster

0.99

busters

0.94

bing

0.93

olean

0.91

ographed

0.82

oons

0.82

ipl

0.80

agy

0.80

Activations Density 0.015%

references to organized crime groups or individuals involved in criminal activities

No Comments

No Known Activations